© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86911
    Prev
    Next
    INDEX
    Explanations

    various time and date-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Date and time information in article metadata sections, particularly publication timestamps and numeric identifiers.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iese
    -0.07
    antan
    -0.07
    cle
    -0.06
    utherland
    -0.06
    aleb
    -0.06
    ÄĻż
    -0.06
    ÑĮ
    -0.06
    rella
    -0.06
     latter
    -0.06
    anzi
    -0.06
    POSITIVE LOGITS
    OVÃģ
    0.07
    dings
    0.06
     минÑĥ
    0.06
    umo
    0.06
     æ½
    0.06
    Instructions
    0.06
     autogenerated
    0.06
    обов
    0.06
    .pull
    0.06
    ÑĢÑĸÑĩ
    0.06
    Activations Density 0.083%

    No Known Activations